Utilizing reinforcement learning for de novo drug design
Journal article, 2024

Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.

Reinforcement learning

De novo drug design

Policy optimization

Replay buffer

Recurrent neural network

Author

Hampus Gummesson Svensson

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

AstraZeneca AB

Christian Tyrchan

AstraZeneca AB

Ola Engkvist

AstraZeneca AB

Chalmers, Computer Science and Engineering (Chalmers)

Morteza Haghir Chehreghani

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Machine Learning

0885-6125 (ISSN) 1573-0565 (eISSN)

Vol. 113 7 4811-4843

Subject Categories

Computer Science

DOI

10.1007/s10994-024-06519-w

More information

Latest update

7/2/2024 5